Tetris3D: 3D Scene Generation With Objects That Fit Together Paper • 2610.10539 • Published 13 days ago • 49
LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation Paper • 2610.12442 • Published 12 days ago • 45
HuRo: Robotizing Human Videos for Scalable VLA Pretraining Paper • 2609.10706 • Published Sep 18 • 29
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding Paper • 2608.07663 • Published Aug 7 • 23
Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views Paper • 2606.29513 • Published Jun 28 • 52
Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking Paper • 2606.15673 • Published Apr 8 • 13
Rethinking State Tracking in Recurrent Models Through Error Control Dynamics Paper • 2605.07755 • Published May 8 • 22